Artificial Intelligence Software Changes Rare Disease Testing Strategy in Real Time: An International Case Series Using Face2Gene

Natasha L Rudy; Adriana Gomes; Tinatin Tkemaladze; Omar Abdul-Rahman; Drew Cratsenberg; Giulia Pascolini; Giovanni Di Zenzo; Daniele Castiglia; Emily Black; Camerun Washington; Lauren Chad; Cynthia Curry; Miguel Del Campo; Nicole Fleischer; Lynne M Bird; Anna C E Hurst

doi:10.1002/ajmg.a.64171

Artificial Intelligence Software Changes Rare Disease Testing Strategy in Real Time: An International Case Series Using Face2Gene

Am J Med Genet A. 2025 Jul 4:e64171. doi: 10.1002/ajmg.a.64171. Online ahead of print.

Authors

Natasha L Rudy¹, Adriana Gomes², Tinatin Tkemaladze^{3

4}, Omar Abdul-Rahman⁵, Drew Cratsenberg⁶, Giulia Pascolini⁷, Giovanni Di Zenzo⁸, Daniele Castiglia⁸, Emily Black¹, Camerun Washington¹, Lauren Chad^{9

10

11}, Cynthia Curry¹², Miguel Del Campo², Nicole Fleischer¹³, Lynne M Bird², Anna C E Hurst¹⁴

Affiliations

¹ Greenwood Genetic Center, Greenville, South Carolina, USA.
² Department of Pediatrics and Rady Children's Hospital, Division of Dysmorphology/Genetics, University of California San Diego, San Diego, California, USA.
³ Department of Molecular and Medical Genetics, Tbilisi State Medical University, Tbilisi, Georgia.
⁴ Givi Zhvania Pediatric Academic Clinic, Tbilisi State Medical University, Tbilisi, Georgia.
⁵ Department of Pediatrics, New York-Presbyterian Weill Cornell Medicine, New York, New York, USA.
⁶ Genetic Medicine Division, Munroe-Meyer Institute for Genetics and Rehabilitation, University of Nebraska Medical Center, Omaha, Nebraska, USA.
⁷ Rare Diseases Center, Istituto Dermopatico dell'Immacolata, IDI-IRCCS, Rome, Italy.
⁸ Molecular and Cell Biology Laboratory, Istituto Dermopatico dell'Immacolata, IDI-IRCCS, Rome, Italy.
⁹ The Hospital for Sick Children, Toronto, Ontario, Canada.
¹⁰ Division of Clinical and Metabolic Genetics, The Hospital for Sick Children, Toronto, Ontario, Canada.
¹¹ Department of Paediatrics, University of Toronto, Toronto, Ontario, Canada.
¹² Department of Pediatrics, Genetic Medicine, University of California San Francisco/Fresno, California, USA.
¹³ FDNA Inc, Boston, Massachusetts, USA.
¹⁴ Department of Genetics, University of Alabama at Birmingham, Birmingham, Alabama, USA.

PMID: 40613735
DOI: 10.1002/ajmg.a.64171

Abstract

Genetic disorders commonly share features such as developmental delays, cognitive impairment, and behavioral challenges, yet many conditions also present unique dysmorphic features that distinguish them. Performing a thorough medical and family history and a detailed physical exam with attention to dysmorphic features is often the first step toward arriving at a genetic diagnosis. Synthesizing a differential diagnosis from the information gathered helps to guide the genetic testing strategy. Challenges to recognizing a disorder include the breadth of the clinician's prior experience, the lack of distinctive dysmorphology or overlapping dysmorphology in some conditions, atypical presentations, and difficulties identifying phenotypes across different ancestries. In cases where such challenges exist, advanced facial recognition technology can help the consulting expert by directing a more efficient test strategy. We present 17 cases involving 19 patients, including one pair of affected siblings and one case involving a child and her affected mother, for which DeepGestalt, the technology powering Face2Gene, changed medical geneticists' testing decisions. These cases illustrate how this form of artificial intelligence can provide clinical utility through influencing providers' genetic testing recommendations in real time.

Keywords: DeepGestalt; Face2Gene; artificial intelligence system; computer‐aided facial phenotyping tool.